{"id":15053241,"url":"https://github.com/soham2002/docuchat","last_synced_at":"2026-02-08T23:35:20.140Z","repository":{"id":257429872,"uuid":"858191714","full_name":"soham2002/DocuChat","owner":"soham2002","description":"DocuChatv1 using Colab, Pinecone, and Hugging Face, and DocuChatv2 with Streamlit, GeminiPro, and FAISS.","archived":false,"fork":false,"pushed_at":"2024-09-17T13:05:22.000Z","size":227,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-20T13:12:37.110Z","etag":null,"topics":["faiss","gemini-pro","huggingface","langchain-python","llama2","pinecone","streamlit"],"latest_commit_sha":null,"homepage":"https://docuchat-pdf.streamlit.app/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/soham2002.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-09-16T13:23:38.000Z","updated_at":"2024-10-18T18:24:00.000Z","dependencies_parsed_at":"2024-09-29T03:00:50.618Z","dependency_job_id":"5d1fb613-27c9-4b26-afe0-f9c8a77308ec","html_url":"https://github.com/soham2002/DocuChat","commit_stats":null,"previous_names":["soham2002/docuchat"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/soham2002%2FDocuChat","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/soham2002%2FDocuChat/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/soham2002%2FDocuChat/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/soham2002%2FDocuChat/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/soham2002","download_url":"https://codeload.github.com/soham2002/DocuChat/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":234794114,"owners_count":18887686,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["faiss","gemini-pro","huggingface","langchain-python","llama2","pinecone","streamlit"],"created_at":"2024-09-24T21:37:52.907Z","updated_at":"2025-09-30T23:31:19.085Z","avatar_url":"https://github.com/soham2002.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DocuChat\n### DocuChatv1\n[Click Here](https://colab.research.google.com/drive/1cefEldBlukCTfm-x_Qpg3hgwompKm1qQ?usp=sharing) to view Google Colab based implimentation of a PDF Chat Bot where the Uploaded PDF is embedded into a VectorDB (here Pinecone) and proper search query to fetch desired answers from the uploaded PDF.\n\n### DocuChatv2\n[Click Here](https://docuchat-pdf.streamlit.app/) to view the deployed DocuChat Model with GeminiPro and FAISS VectorEmbedding.\n\n## How to run DocuChatv1?\nTo use the DocuChatv1 in Google Colab,follow these steps:\n\n 1. Visit the Google colab file by clicking [here](https://colab.research.google.com/drive/1cefEldBlukCTfm-x_Qpg3hgwompKm1qQ?usp=sharing)\n 2. Create a copy of the Colab file on your drive\n \n 3. Generate Pinecone API Key:\n    1. Once logged in, navigate to the API Keys section in the Pinecone dashboard.\n    2. Click on Create API Key and copy the generated key.\n      \n 5. Create a Pinecone Index:\n    1. Click on Create Index.\n    2. Choose an index name, set the dimension (e.g., 768 for BERT-based models), and specify the metric (e.g., cosine similarity).\n    3. Click Create.\n \n 6. Change the Index Name to your own Index Name\n```bash\npc = Pinecone(api_key=PINECONE_API_KEY)\nindex_name = pc.Index('ragchat') #change it to your pinecone index name\n\nfrom langchain.vectorstores import Pinecone as PC\n\nos.environ['PINECONE_API_KEY']\n\ndocs_chunks = [t.page_content for t in docs]\npinecone_index = PC.from_texts(\n    docs_chunks,\n    embeddings,\n    index_name='ragchat' #change it to your Pinecone Index\n\n)\n```\n\n6. Set Up Hugging Face API\n   1. Create a Hugging Face Account:\n   2. Go to Hugging Face and sign up or log in.\n      \n7. Generate Hugging Face Acess Token:\n    1. Navigate to the Settings section of your Hugging Face account.\n    2. Under Access Tokens, create a new token and copy it.\n       \n8. Add the API Keys to Colab:\n   1. Add all the API Keys to the Secrets section of your Colab File\n9. Run all the cells of the Colab File\n\n![Alt text](https://github.com/soham2002/DocuChat/blob/main/static/SCG.png)\n\n## How to run DocuChatv2?\nTo use the DocuChatv2 in your local system,follow these steps:\n\n1. Install the required Python packages:\n\n    ```bash\n    pip install requirements.txt\n    ```\n2. Create a .env file:\n   ```bash\n   GEMINI_API_KEY = \"Enter your Gemini Api Key\"\n   ```\n4. Run the DocuChatv2 by running the following code in the terminal:\n\n      ```bash\n      streamlit run app.py\n      ```\n5. You are good to go!\n![Alt text](https://github.com/soham2002/DocuChat/blob/main/static/DocuChat_SC.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsoham2002%2Fdocuchat","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsoham2002%2Fdocuchat","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsoham2002%2Fdocuchat/lists"}